<![CDATA[Urban transport systems in tropical cities are under increasing strain due to rapid population growth, rising mobility demand, and climate-induced stresses. These conditions create highly complex, dynamic interactions among users, vehicles, infrastructure, and environmental factors that are difficult to capture with conventional modeling approaches. Most existing transport planning frameworks rely on static or single-agent models, limiting their ability to represent real-time feedback and adaptive behavior, particularly in tropical megacities characterized by congestion, climatic volatility, and socio-economic diversity. This paper introduces a multi-agent artificial intelligence (AI) simulation framework designed as an exploratory tool for evaluating the sustainability of urban transportation infrastructure. The proposed framework integrates dynamic systems theory with multi-agent reinforcement learning to simulate interactions among heterogeneous transport agents and infrastructure components. Synthetic data reflecting typical tropical urban conditions are employed to enable controlled experimentation across multiple scenarios, including baseline, optimized infrastructure, and adaptive AI control settings. Simulation results indicate that adaptive AI scenarios outperform baseline configurations, demonstrating 25.6% higher energy efficiency, 31.4% lower congestion, and 21.8% lower emissions in the modeled environment. These outcomes illustrate the potential of the proposed framework to support comparative sustainability evaluation rather than direct real-world performance validation.]]>
